View on GitHub

NewsHack 2018

Editorial Tools for Global News

[API Documentation] [Open Source information]

Welcome to the 2018 SUMMA #newsHACK on Editorial Tools for Global News

In collaboration with Summa and Deutsche Welle, BBC News Labs and BBC Connected are inviting journalists, developers and designers to dream up new applications for cutting-edge language technologies in global newsrooms.

What is SUMMA?

Financed by the EU’s Horizon 2020 fund, Scalable Understanding of Multilingual MediA (Summa) is a pan-European project exploring how automation and algorithms can help journalists keep abreast of global news. After nearly three years of development, the team is close to completing a monitoring platform that allows journalists to make sense of the news as it breaks — no matter the language or format.

The Hack Brief

SUMMA API

The SUMMA platform’s API will be available to hack participants. The SUMMA platform will perform the following metadata enrichment operations:

Feature Description
Translation to English Runs only when a non-English language is detected
Named Entity Recognition Tagging of recognised people, places, things, etc. in the text
Topic Detection Tagging of topics covered by the text
Summarisation A small number of sentences summarising the input text
Clustering Associating stories that are “similar”

Available Translations

The version of the platform available to participants will translate from the following languages into English.


Problems, suggestions, missing information?

Contact Andrew Secker via email: andrew.secker@bbc.co.uk or find him in person at the venue.